© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11277
    Prev
    Next
    INDEX
    Explanations

    I followed by verbs or 'don't'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    好åIJĹ
    -0.10
    leccion
    -0.10
    好åIJ§
    -0.10
    åIJĮæĹ¶ä¹Łæĺ¯
    -0.09
    ç«Łæĺ¯
    -0.09
    çĦ¶åIJİåĨį
    -0.09
    ä¸įè´Ł
    -0.09
    inho
    -0.09
    æ´ĭæ´ĭ
    -0.09
    çĽ¸ä¼´
    -0.09
    POSITIVE LOGITS
    ç¹ŀ
    0.09
    建议
    0.08
    çľĭæĿ¥
    0.08
    ç»ķ
    0.08
    èļģ
    0.08
    íĢ´
    0.08
    å¾Ī好
    0.08
    inks
    0.08
    çªĥ
    0.08
    ä¸įå°ij
    0.08
    Activations Density 0.150%

    No Known Activations